aalv2 commited on
Commit
bf083f0
·
verified ·
1 Parent(s): 1ff3cc9

Run 8. Outer Step 36. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +99 -99
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,34 +2,34 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "SUCCESS",
6
- "10": "FAIL",
7
  "100": "NON_PARTICIPATING",
8
- "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
- "105": "SUCCESS",
13
- "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
  "111": "SUCCESS",
20
- "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
- "115": "SUCCESS",
24
- "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "FAIL",
31
- "122": "SUCCESS",
32
- "123": "SUCCESS",
33
  "124": "FAIL",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
@@ -37,10 +37,10 @@
37
  "128": "FAIL",
38
  "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
- "130": "NON_PARTICIPATING",
41
- "131": "NOT_ALIVE",
42
- "132": "SUCCESS",
43
- "133": "SUCCESS",
44
  "134": "SUCCESS",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
@@ -50,144 +50,144 @@
50
  "14": "SUCCESS",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
- "142": "NON_PARTICIPATING",
54
- "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
- "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
- "147": "SUCCESS",
59
- "148": "SUCCESS",
60
- "149": "NON_PARTICIPATING",
61
- "15": "SUCCESS",
62
- "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "FAIL",
66
  "154": "NON_PARTICIPATING",
67
- "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
- "157": "NON_PARTICIPATING",
70
- "158": "SUCCESS",
71
  "159": "NON_PARTICIPATING",
72
- "16": "FAIL",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NOT_ALIVE",
75
  "162": "SUCCESS",
76
- "163": "SUCCESS",
77
  "164": "NON_PARTICIPATING",
78
- "165": "SUCCESS",
79
  "166": "SUCCESS",
80
- "167": "NOT_ALIVE",
81
- "168": "NOT_ALIVE",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
- "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
- "172": "NON_PARTICIPATING",
87
- "173": "NON_PARTICIPATING",
88
  "174": "SUCCESS",
89
- "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
- "180": "NOT_ALIVE",
96
- "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
- "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "SUCCESS",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
- "194": "SUCCESS",
111
- "195": "SUCCESS",
112
- "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "SUCCESS",
121
  "203": "FAIL",
122
- "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
- "208": "NOT_ALIVE",
127
- "209": "NOT_ALIVE",
128
  "21": "FAIL",
129
  "210": "SUCCESS",
130
  "211": "FAIL",
131
- "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
- "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "SUCCESS",
149
- "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "SUCCESS",
155
- "234": "FAIL",
156
- "235": "SUCCESS",
157
- "236": "FAIL",
158
- "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
- "239": "NON_PARTICIPATING",
161
- "24": "SUCCESS",
162
  "240": "FAIL",
163
- "241": "SUCCESS",
164
- "242": "FAIL",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
  "246": "SUCCESS",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
- "249": "FAIL",
172
  "25": "SUCCESS",
173
- "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
  "252": "FAIL",
176
- "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "FAIL",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
- "3": "SUCCESS",
184
- "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "SUCCESS",
190
- "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
@@ -196,22 +196,22 @@
196
  "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
- "44": "FAIL",
200
  "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
- "47": "FAIL",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "SUCCESS",
212
- "56": "SUCCESS",
213
  "57": "SUCCESS",
214
- "58": "SUCCESS",
215
  "59": "SUCCESS",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
@@ -224,37 +224,37 @@
224
  "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
- "7": "FAIL",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
- "73": "SUCCESS",
232
  "74": "SUCCESS",
233
- "75": "NOT_ALIVE",
234
- "76": "NOT_ALIVE",
235
- "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
- "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
  "84": "FAIL",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
- "87": "FAIL",
247
- "88": "FAIL",
248
  "89": "NON_PARTICIPATING",
249
- "9": "SUCCESS",
250
  "90": "NOT_ALIVE",
251
- "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
- "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6358845,
268
- 6358873
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 85,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6358266,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "FAIL",
6
+ "10": "SUCCESS",
7
  "100": "NON_PARTICIPATING",
8
+ "101": "FAIL",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
+ "105": "NOT_ALIVE",
13
+ "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
  "111": "SUCCESS",
20
+ "112": "FAIL",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
+ "115": "NOT_ALIVE",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "SUCCESS",
31
+ "122": "FAIL",
32
+ "123": "FAIL",
33
  "124": "FAIL",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
 
37
  "128": "FAIL",
38
  "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
+ "130": "NOT_ALIVE",
41
+ "131": "NON_PARTICIPATING",
42
+ "132": "NOT_ALIVE",
43
+ "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
 
50
  "14": "SUCCESS",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
+ "142": "FAIL",
54
+ "143": "SUCCESS",
55
  "144": "SUCCESS",
56
+ "145": "SUCCESS",
57
  "146": "SUCCESS",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "FAIL",
60
+ "149": "FAIL",
61
+ "15": "FAIL",
62
+ "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "FAIL",
66
  "154": "NON_PARTICIPATING",
67
+ "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
+ "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
72
+ "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "SUCCESS",
75
  "162": "SUCCESS",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
+ "167": "NON_PARTICIPATING",
81
+ "168": "FAIL",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
+ "172": "NOT_ALIVE",
87
+ "173": "FAIL",
88
  "174": "SUCCESS",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "FAIL",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
+ "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
+ "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
+ "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "SUCCESS",
106
+ "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
+ "194": "FAIL",
111
+ "195": "NOT_ALIVE",
112
+ "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "SUCCESS",
121
  "203": "FAIL",
122
+ "204": "FAIL",
123
  "205": "SUCCESS",
124
+ "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
+ "208": "SUCCESS",
127
+ "209": "FAIL",
128
  "21": "FAIL",
129
  "210": "SUCCESS",
130
  "211": "FAIL",
131
+ "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "FAIL",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "FAIL",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "SUCCESS",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
+ "230": "FAIL",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "SUCCESS",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
+ "239": "FAIL",
161
+ "24": "FAIL",
162
  "240": "FAIL",
163
+ "241": "FAIL",
164
+ "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
  "246": "SUCCESS",
169
+ "247": "SUCCESS",
170
  "248": "NOT_ALIVE",
171
+ "249": "SUCCESS",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "FAIL",
176
+ "253": "FAIL",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
+ "3": "NOT_ALIVE",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "FAIL",
190
+ "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
 
196
  "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
+ "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
+ "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "FAIL",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "SUCCESS",
212
+ "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
+ "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
 
224
  "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
+ "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
+ "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
+ "75": "SUCCESS",
234
+ "76": "FAIL",
235
+ "77": "FAIL",
236
  "78": "NON_PARTICIPATING",
237
+ "79": "FAIL",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
+ "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
  "84": "FAIL",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
+ "87": "SUCCESS",
247
+ "88": "SUCCESS",
248
  "89": "NON_PARTICIPATING",
249
+ "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
+ "91": "FAIL",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
+ "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6358966,
268
+ 6358994
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
+ "inner_step": 9,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6358925,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7403d34b15628d3136cb632763382f6ed3984b31fd68ffc11d3464dcbe218ad4
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71dd0a5669a538bee8b7f852b867e4b2858e1d16e5f72535c12f6147a313e969
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19c598192a89b54c7435ef289392a6e3c17e5ff2d1a602744b0369041530608d
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b1467a398c26ba44d5ab1ab6cd61980940b852148233edb98736aee571d7e6d
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed6b23e7768f6d594328c8713373423bfb78cc98302b843bf5b8669322d69e00
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0bcd6ffa75b26208cc72e40a74efd21230cad9c2180baaec43e2cc853749a0e
3
  size 4400216536